pith. sign in

arXiv preprint arXiv:2507.15868v1 , year=

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learning Perturbations to Extrapolate Your LLM

stat.ML · 2026-05-13 · unverdicted · novelty 6.0

A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Perturbations to Extrapolate Your LLM stat.ML · 2026-05-13 · unverdicted · none · ref 60

    A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.